compute_performances_and_costs

// WHEN AI AGENTS USE THIS TOOL

AI agents use compute_performances_and_costs to create or modify resources in AWS DynamoDB MCP Server. Write operations carry medium risk because an autonomous agent could trigger bulk unintended modifications. Rate limits prevent a single agent session from making hundreds of changes in rapid succession. Argument validation ensures the agent passes expected values.

// WHY ENFORCE A POLICY ON COMPUTE_PERFORMANCES_AND_COSTS

Without a policy, an AI agent could call compute_performances_and_costs repeatedly, creating or modifying resources faster than any human could review. Intercept's rate limiting ensures write operations happen at a controlled pace, and argument validation catches malformed or unexpected inputs before they reach AWS DynamoDB MCP Server.

// RECOMMENDED POLICY

Write tools can modify data. A rate limit prevents runaway bulk operations from AI agents.

aws-dynamodb-mcp-server.yaml

tools:
  compute_performances_and_costs:
    rules:
      - action: allow
        rate_limit:
          max: 30
          window: 60

See the full AWS DynamoDB MCP Server policy for all 8 tools.

// DETAILS

Tool Name compute_performances_and_costs

Category Write

MCP Server AWS DynamoDB MCP Server MCP Server

Risk Level Medium

// MORE AWS DYNAMODB MCP SERVER TOOLS

Execute source_db_analyzer Write generate_data_access_layer Write generate_resources Read dynamodb_data_model_schema_converter Read dynamodb_data_model_schema_validator Read dynamodb_data_model_validation Read dynamodb_data_modeling

// WHAT CAN GO WRONG

Agents calling write-class tools like compute_performances_and_costs have been implicated in these attack patterns. Read the full case and prevention policy for each:

Browse the full MCP Attack Database →

// OTHER WRITE TOOLS ACROSS MCP SERVERS

Other tools in the Write risk category across the catalogue. The same policy patterns (rate-limit, validate) apply to each.

Firecrawl Web Scraping Server firecrawl_generate_llmstxt AbraFlexi contact_create AbraFlexi contact_update AbraFlexi evidence_create AbraFlexi evidence_update AbraFlexi invoice_issued_update

// RELATED READING

// FAQ

What does the compute_performances_and_costs tool do? +

Calculate DynamoDB capacity units and monthly costs from access patterns. Call after completing data model design. Extracts patterns from Access Pattern Mapping table and tables from Table Designs section in dynamodb_data_model.md. Args: access_pattern_list: Access patterns with fields: - operation: GetItem|Query|Scan|PutItem|UpdateItem|DeleteItem|BatchGetItem|BatchWriteItem|TransactGetItems|TransactWriteItems - pattern, description, table, rps (>0), item_size_bytes (1-409600) - item_count: required for Query/Scan/Batch/Transact operations (>0) - strongly_consistent: optional for GetItem/Query/Scan/BatchGetItem (default: false) - gsi: optional for Query/Scan (target index name) - gsi_list: optional for write operations (affected index names) table_list: Tables with name, item_count (>0), item_size_bytes (1-409600), gsi_list (each GSI needs name, item_count, item_size_bytes) workspace_dir: Absolute path to the folder containing dynamodb_data_model.md - report will be appended Returns: {'status': 'success', 'message': <success_message>} or {'status': 'error', 'message': <error_reason>} Example: { "access_pattern_list": [ { "operation": "GetItem", "pattern": "get-user", "description": "Get user by ID", "table": "users", "rps": 100, "item_size_bytes": 2000 }, { "operation": "Query", "pattern": "query-by-email", "description": "Query user by email", "table": "users", "rps": 50, "item_size_bytes": 1500, "item_count": 1, "gsi": "email-index" }, { "operation": "PutItem", "pattern": "put-user", "description": "Create user", "table": "users", "rps": 20, "item_size_bytes": 2000, "gsi_list": ["email-index", "status-index"] }, { "operation": "Query", "pattern": "query-orders", "description": "Query user orders", "table": "orders", "rps": 50, "item_size_bytes": 800, "item_count": 10 } ], "table_list": [ { "name": "users", "item_size_bytes": 2500, "item_count": 10000, "gsi_list": [ {"name": "email-index", "item_size_bytes": 1500, "item_count": 10000}, {"name": "status-index", "item_size_bytes": 500, "item_count": 10000} ] }, { "name": "orders", "item_size_bytes": 1024, "item_count": 50000 } ], "workspace_dir": "/absolute/path/to/workspace" }. It is categorised as a Write tool in the AWS DynamoDB MCP Server MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on compute_performances_and_costs? +

Add a rule in your Intercept YAML policy under the tools section for compute_performances_and_costs. You can allow, deny, rate-limit, or validate arguments. Then run Intercept as a proxy in front of the AWS DynamoDB MCP Server MCP server.

What risk level is compute_performances_and_costs? +

compute_performances_and_costs is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit compute_performances_and_costs? +

Yes. Add a rate_limit block to the compute_performances_and_costs rule in your Intercept policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.

How do I block compute_performances_and_costs completely? +

Set action: deny in the Intercept policy for compute_performances_and_costs. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.

What MCP server provides compute_performances_and_costs? +

compute_performances_and_costs is provided by the AWS DynamoDB MCP Server MCP server (awslabs.dynamodb-mcp-server). Intercept sits as a proxy in front of this server to enforce policies before tool calls reach the server.

compute_performances_and_costs

Let agents act without letting them run wild.